Extensions/Gemma 4 - Multimodal AI
ComfyUI Extension

Gemma 4 - Multimodal AI

ComfyUI custom nodes for Gemma 4 multimodal AI

By mailzwj·Created 3 months ago·Updated 3 months ago· 1
mailzwj/ComfyUI-Gemma4
Nodes4
On cloudLocal install
CategoryGemma4
Stars1
Updated3 months ago

Nodes (4)

Gemma 4 Image Understanding

Gemma 4 that reads your image on your own GPU — no API, no Ollama

Gemma4
Gemma 4 Multimodal

One Gemma 4 node for text, images, and video — the everything bucket

Gemma4
Gemma 4 Text Generation

Gemma 4 text generation without the vision — the local prompt engine

Gemma4
Gemma 4 Video Understanding

Gemma 4 watching your video frames — captions without a video model

Gemma4
Readme

ComfyUI-Gemma4

ComfyUI 自定义节点，集成 Gemma 4 多模态大模型，支持文本生成、图像理解与视频理解。

工作流

节点列表

| 节点 | 说明 | |------|------| | Gemma 4 Multimodal | 统一节点，支持纯文本、图像和视频输入 | | Gemma 4 Text Generation | 纯文本生成 | | Gemma 4 Image Understanding | 单图或多图（序列帧）理解 | | Gemma 4 Video Understanding | 视频帧理解，支持帧采样 |

模型安装

从 ModelScope 下载模型，放置到以下目录：

ComfyUI/models/LLM/gemma-4-12b-it/

目录结构

models
  |- LLM
    |- gemma-4-12b-it
      |- chat_template.jinja
      |- config.json
      |- configuration.json
      |- generation_config.json
      |- model.safetensors
      |- processor_config.json
      |- README.md
      |- tokenizer.json
      |- tokenizer_config.json

安装使用

  1. 将本仓库克隆到 ComfyUI/custom_nodes/ 目录
  2. 安装依赖：pip install -r requirements.txt
  3. 重启 ComfyUI

许可证

Apache-2.0